Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MIA-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal Instruction FollowingMIA-Bench
Score8.86
12
Membership InferenceMIA-Bench 5% Forget Set
Average Performance69.6
12
Multi-modal human-preference alignmentMIA-Bench
Score89.6
6
Showing 3 of 3 rows